Download Latest Version Adapters v1.2.0 source code.tar.gz (15.2 MB)
Email in envelope

Get an email when there's a new version of Adapters

Home / v1.0.0
Name Modified Size InfoDownloads / Week
Parent folder
Adapters v1.0.0 source code.tar.gz 2024-08-10 15.1 MB
0
Adapters v1.0.0 source code.zip 2024-08-10 15.3 MB
0
README.md 2024-08-10 1.3 kB
0
Totals: 3 Items   30.4 MB 0

Blog post: https://adapterhub.ml/blog/2024/08/adapters-update-reft-qlora-merging-models

This version is built for Hugging Face Transformers v4.43.x.

New Adapter Methods & Model Support

  • Add Representation Fine-Tuning (ReFT) implementation (LoReFT, NoReFT, DiReFT) (@calpt via [#705])
  • Add LoRA weight merging with Task Arithmetics (@lenglaender via [#698])
  • Add Whisper model support + notebook (@TimoImhof via [#693]; @julian-fong via [#717])
  • Add Mistral model support (@KorventennFR via [#609])
  • Add PLBart model support (@FahadEbrahim via [#709])

Breaking Changes & Deprecations

  • Remove support for loading from archived Hub repository (@calpt via [#724])
  • Remove deprecated add_fusion() & train_fusion() methods (@calpt via [#714])
  • Remove deprecated arguments in push_adapter_to_hub() method (@calpt via [#724])
  • Deprecate support for passing Python lists to adapter activation (@calpt via [#714])

Minor Fixes & Changes

  • Upgrade supported Transformers version (@calpt & @lenglaender via [#712], [#719], [#727])
  • Fix SDPA/ Flash attention support for Llama (@calpt via [#722])
  • Fix gradient checkpointing for Llama and for Bottleneck adapters (@calpt via [#730])
Source: README.md, updated 2024-08-10